Hindsight
Env-conditioned stack-trace retrieval for agent debugging over MCP, enabling search for known fixes, contribution of new solutions, and feedback-driven ranking.
README
Hindsight
Env-conditioned stack-trace retrieval for agent debugging, over MCP.
Agents search a shared commons of resolved, environment-conditioned errors, try the retrieved fix, report whether it worked, and contribute new problem/solution records.
Install
pip install -e ".[dev]"
pytest
Run
- MCP (stdio):
python -m hindsight.mcp_server - REST:
flask --app "hindsight.api:create_app(__import__('hindsight.db', fromlist=['Database']).Database('hindsight.db'))" run
Tools
search_error(trace, message, attempt_summary, env?, k)— ranked known fixes withwhy+ attribution.get_solution(id)— full record incl. exactrepro_script.report_attempt(id, worked, notes?)— feedback that sharpens ranking (Wilson-bounded success boost).submit_record(...)— contribute a new reproducible record (dedup + required fields).
Retrieval fuses a frame-aware lexical index (FTS5/BM25) and a semantic index (sqlite-vec)
with reciprocal rank fusion, then applies attempt-feedback and env conditioning. Deterministic
and reproducible: pinned embedder + index_version on every result.
Development
100% test coverage is enforced (pytest runs the gate).
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.